© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13471
    Prev
    Next
    INDEX
    Explanations

    rotation and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĶ¯çº¿
    -0.09
    æ¡¥åĮº
    -0.08
     Amend
    -0.08
    åıĮåŁİ
    -0.08
    _bridge
    -0.08
    æĭīå¾·
    -0.07
     Proxy
    -0.07
    _abort
    -0.07
     brid
    -0.07
    åħ¶ä»ĸåªĴä½ĵ
    -0.07
    POSITIVE LOGITS
    æĹĭ转
    0.11
     rotate
    0.09
     rotation
    0.09
    Rotation
    0.09
    rotate
    0.09
     rotates
    0.09
    rotation
    0.08
     rotations
    0.08
    Rotate
    0.08
    .rot
    0.08
    Activations Density 0.013%

    No Known Activations